Instructors
Prof. Dr. Christian Wachinger, Fabian Bongratz, Yitong Li, Emre Kavak, Alexandra Samoylova, Martin Rath, Qihang Sun
Contact
If you have any questions regarding this seminar, contact seminars@ai-med.de.
Registration
Registration to the seminar is done via the TUM Matching Platform. Pay attention to the deadlines!!
Announcements
- The pre-course meeting is on 2. February 2026, 1pm via Zoom. Zoom link: https://tum-conf.zoom-x.de/j/64742912887?pwd=sXQ8yG68bO4ZoZKLaHumN1o5vZCoad.1
- Seminar Kick-off will take place on 24. April 2026, 12.30 pm, Seminarraum Holbeinstrasse 11, 3OG. Assignment of papers & get to know your supervisors - attendance is mandatory.
- Paper selection: please submit your three paper choices to seminars@ai-med.de until 23. April 6pm.
- Main seminar dates: 1. & 2. July 2026, 9am-3pm. If main seminar dates do not work for you, please deregister from the course until 1. May.
Please make sure in advance that you can attend both seminar dates, since later deregistration is unfortunately not possible and non-attendance will be graded with 5.0. - Kick-off session slides: ML-Neuro Seminar SS2026 Kickoff.pdf
- Some of the students did not receive a paper from their top-3 list. If you think that the assigned paper is a bad match, please contact us, we'll try to find a solution!
Timeline
- Pre-course meeting: 2. February 2026, 1pm:
- Seminar Kick-off session: 24. April 2026, 12.30 pm, Seminarraum Holbeinstrasse 11, 3OG.
- Main Seminar dates: 1.& 2. July 9am-3pm, attendance is mandatory
- Slide submission via restricted 'Presentation' folder: until 30. June 23:59
- Blogpost submission deadline: 16. July, 2 weeks after main seminar dates.
Topics
tba
| Paper ID | Title | Published in | Link | Group/Supervisor | Student | Additional Material |
|---|---|---|---|---|---|---|
| 1 | Causal Effect Estimation on Imaging and Clinical Data for Treatment Decision Support of Aneurysmal Subarachnoid Hemorrhage | IEEE TMI 2024 | https://doi.org/10.1109/tmi.2024.3390812 | Emre | Tulca Yöney | |
| 2 | Counterfactual Causal-Effect Intervention for Interpretable Medical Visual Question Answering | IEEE TMI 2024 | https://doi.org/10.1109/tmi.2024.3425533 | Emre | Salim Daoud | |
| 3 | Improving Robustness and Reliability in Medical Image Classification With Latent-Guided Diffusion and Nested-Ensembles | IEEE TMI 2025 | https://doi.org/10.1109/TMI.2025.3583974 | Emre | Eda Erusta | |
| 4 | DCT-Net: Dual-branch CT Reconstruction from Orthogonal X-rays with Diffusion Model and Contrastive Learning | MICCAI 2025 | https://papers.miccai.org/miccai-2025/paper/2669_paper.pdf | Martin | Gertrūda Bazytė | |
| 5 | 3D MedDiffusion: A 3D medical latent diffusion model for controllable and high-quality medical image generation | IEEE TMI 2025 | https://doi.org/10.1109/TMI.2025.3585372 | Martin | Zitong Fu | |
| 6 | Treatment-Aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction | IEEE TMI 2025 | https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10851394 | Martin | Nhat Phuong Anh Vu | |
| 7 | CT Diagnostic Mode-Oriented and Cross Difficulty Aware Network for Pulmonary Embolism Segmentation | IEEE TMI 2025 | https://doi.org/10.1109/TMI.2025.3631047 | Qihang | Ons Bahrouni | |
| 8 | QCResUNet: Joint subject-level and voxel-level segmentation quality prediction | Medical Image Analysis (2026) | https://doi.org/10.1016/j.media.2025.103718 | Qihang | Benedikt Münch | |
| 9 | S2CAC: Semi-supervised coronary artery calcium segmentation via scoring-driven consistency and negative sample boosting | Medical Image Analysis (2026) | https://doi.org/10.1016/j.media.2025.103823 | Qihang | Maria Alejandra Sagastume Giron | |
| 10 | Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks | ICLR 2026 | https://doi.org/10.48550/arXiv.2509.22258 | Yitong | Christian Devin | |
| 11 | How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images | ICLR 2026 | https://doi.org/10.48550/arXiv.2603.14323 | Yitong | Tzu-ling Ching | |
| 12 | Learning neuroimaging models from health system scale data | Nature Biomedical Engineering (2026) | https://doi.org/10.48550/arXiv.2509.18638 | Yitong | Amine Smaoui | |
| 13 | Multi-label pathology editing of chest X-rays with a Controlled Diffusion Model | Medical Image Analysis (2025) | https://www.sciencedirect.com/science/article/pii/S1361841525001318 | Alexandra | - | |
| 14 | Aligning machine and human visual representations across abstraction levels | Nature (2025) | https://doi.org/10.1038/s41586-025-09631-6 | Alexandra | Ruiyang Jiang | |
| 15 | A generalizable foundation model for analysis of human brain MRI | Nature (2026) | https://doi.org/10.1038/s41593-026-02202-6 | Alexandra | Ayan Hashimova |
Resources & Material
Giving talks
Doing a TED Talk: The Full Story
The secret structure of great talks
How to Deliver a Great TED Talk